AstraZeneca on AWS: Amazon Bedrock agentic Development Assistant for clinical trials

Use case typeDrug discoveryUpdated Jun 13, 2026

AstraZeneca is a global, science-led biopharmaceutical company focused on discovery, development and commercialization of prescription medicines. The company uses AWS to support research through commercialization, and specifically applies Amazon Bedrock to accelerate clinical trials by combining structured and unstructured data. An agentic AI-powered Development Assistant gives clinical, regulatory, safety, and quality teams conversational access to trusted insights in seconds.

Organization
AstraZeneca
Industry
Pharma
Published
May 2026

Reported outcomes

Strategic outcomes

Speed & agilityFaster access to trial insightsNew product / capabilityDeployed agentic development assistantBetter decisions & insightTrusted insights across trial data

Primary read

Use case focus

Showing 3 of 5

  • 1Clinical trials
  • 2Drug development
  • 3Research assistant
  • Clinical trial workflows are complex and require fast access to reliable insights across structured and unstructured data.
  • Teams across clinical, regulatory, safety, and quality functions need quicker retrieval of trusted information to support development decisions.
  • AstraZeneca uses Amazon Bedrock with text-to-SQL and retrieval-augmented generation (RAG).
  • The solution is an agentic AI-powered Development Assistant that provides conversational access to insights.
  • The implementation is described as modular and multi-agent, combining data modalities and improving data reliability.
  • The assistant enables teams to access trial-related insights in seconds.
  • The goal is to accelerate drug development and advance AstraZeneca's clinical trials transformation.
  • The article presents the solution as already in production use across critical development workflows.
Architecture

AstraZeneca's Development Assistant uses Amazon Bedrock with text-to-SQL and retrieval-augmented generation to merge structured and unstructured data. The article describes an agentic, modular multi-agent design that exposes trusted insights through a conversational interface for clinical development teams.

Sources & evidence1
Groundedness: 5/5Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases
This website uses cookies to enhance the user experience. Learn more.